SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection

Yan, Weiqi; Chen, Lvhai; Zhang, Shengchuan; Zhang, Yan; Cao, Liujuan

doi:10.24963/ijcai.2025/242

SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection

Weiqi Yan, Lvhai Chen, Shengchuan Zhang, Yan Zhang, Liujuan Cao

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 2170-2178.

https://doi.org/10.24963/ijcai.2025/242

Keywords

Computer Vision: CV: Image and video retrieval
Computer Vision: CV: Segmentation, grouping and shape analysis
Computer Vision: CV: Recognition (object detection, categorization)

Abstract

The difficulty of pixel-level annotation has significantly hindered the development of the Camouflaged Object Detection (COD) field. To save on annotation costs, previous works leverage the semi-supervised COD framework that relies on a small number of labeled data and a large volume of unlabeled data. We argue that there is still significant room for improvement in the effective utilization of unlabeled data. To this end, we introduce a Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection (SCOUT). It includes an Adaptive Data Augment and Selection (ADAS) module and a Text Fusion Module (TFM). The ADSA module selects valuable data for annotation through an adversarial augment and sampling strategy. The TFM module further leverages the selected valuable data by combining camouflage-related knowledge and text-visual interaction. To adapt to this work, we build a new dataset, namely RefTextCOD. Extensive experiments show that the proposed method surpasses previous semi-supervised methods in the COD field and achieves state-of-the-art performance. Our code will be released at https://github.com/Heartfirey/UCOD-DPL.

Weiqi Yan, Lvhai Chen, Shengchuan Zhang, Yan Zhang, and Liujuan Cao. 2025. SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 2170–2178. https://doi.org/10.24963/ijcai.2025/242

@inproceedings{ijcai2025p242,
  title     = {SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection},
  author    = {Yan, Weiqi and Chen, Lvhai and Zhang, Shengchuan and Zhang, Yan and Cao, Liujuan},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {2170--2178},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/242},
  url       = {https://doi.org/10.24963/ijcai.2025/242},
}

TY  - CPAPER
TI  - SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection
AU  - Yan, Weiqi
AU  - Chen, Lvhai
AU  - Zhang, Shengchuan
AU  - Zhang, Yan
AU  - Cao, Liujuan
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 2170
EP  - 2178
DO  - 10.24963/ijcai.2025/242
UR  - https://doi.org/10.24963/ijcai.2025/242
ER  -